Workload-Driven HBF Substrate For Capacity-Scalable LLM Inference (Huawei, ETH Zurich, HUST)

Researchers at Huawei, ETH Zürich, and HUST published a technical paper titled “FLINT: Efficiently Leveraging High Bandwidth Flash for Capacity-Scalable LLM Inference Acceleration.” Abstract: “LLM inference is increasingly constrained by accelerator memory capacity rather than compute throughput. This constraint is especially acute in single-accelerator and small-node inference systems, where limited on-package memory capacity restricts the size of deployable models. HBF is an emerging 3D-stacke